Paper Group NANR 178
Adapting Topic Models using Lexical Associations with Tree Priors. Learning to Rank Semantic Coherence for Topic Segmentation. Detecting Sarcasm Using Different Forms Of Incongruity. Automatic Difficulty Assessment for Chinese Texts. Model evidence from nonequilibrium simulations. Crossing the border twice: Reimporting prepositions to alleviate L1- …
Adapting Topic Models using Lexical Associations with Tree Priors
| Title | Adapting Topic Models using Lexical Associations with Tree Priors |
| Authors | Weiwei Yang, Jordan Boyd-Graber, Philip Resnik |
| Abstract | Models work best when they are optimized taking into account the evaluation criteria that people care about. For topic models, people often care about interpretability, which can be approximated using measures of lexical association. We integrate lexical association into topic optimization using tree priors, which provide a flexible framework that can take advantage of both first order word associations and the higher-order associations captured by word embeddings. Tree priors improve topic interpretability without hurting extrinsic performance. |
| Tasks | Machine Translation, Topic Models, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1203/ |
| https://www.aclweb.org/anthology/D17-1203 | |
| PWC | https://paperswithcode.com/paper/adapting-topic-models-using-lexical |
| Repo | |
| Framework | |
Learning to Rank Semantic Coherence for Topic Segmentation
| Title | Learning to Rank Semantic Coherence for Topic Segmentation |
| Authors | Liang Wang, Sujian Li, Yajuan Lv, Houfeng Wang |
| Abstract | Topic segmentation plays an important role for discourse parsing and information retrieval. Due to the absence of training data, previous work mainly adopts unsupervised methods to rank semantic coherence between paragraphs for topic segmentation. In this paper, we present an intuitive and simple idea to automatically create a {``}quasi{''} training dataset, which includes a large amount of text pairs from the same or different documents with different semantic coherence. With the training corpus, we design a symmetric CNN neural network to model text pairs and rank the semantic coherence within the learning to rank framework. Experiments show that our algorithm is able to achieve competitive performance over strong baselines on several real-world datasets. | |
| Tasks | Common Sense Reasoning, Information Retrieval, Learning-To-Rank, Topic Models |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1139/ |
| https://www.aclweb.org/anthology/D17-1139 | |
| PWC | https://paperswithcode.com/paper/learning-to-rank-semantic-coherence-for-topic |
| Repo | |
| Framework | |
Detecting Sarcasm Using Different Forms Of Incongruity
| Title | Detecting Sarcasm Using Different Forms Of Incongruity |
| Authors | Aditya Joshi |
| Abstract | Sarcasm is a form of verbal irony that is intended to express contempt or ridicule. Often quoted as a challenge to sentiment analysis, sarcasm involves use of words of positive or no polarity to convey negative sentiment. Incongruity has been observed to be at the heart of sarcasm understanding in humans. Our work in sarcasm detection identifies different forms of incongruity and employs different machine learning techniques to capture them. This talk will describe the approach, datasets and challenges in sarcasm detection using different forms of incongruity. We identify two forms of incongruity: incongruity which can be understood based on the target text and common background knowledge, and incongruity which can be understood based on the target text and additional, specific context. The former involves use of sentiment-based features, word embeddings, and topic models. The latter involves creation of author{'}s historical context based on their historical data, and creation of conversational context for sarcasm detection of dialogue. |
| Tasks | Sarcasm Detection, Sentiment Analysis, Topic Models, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5201/ |
| https://www.aclweb.org/anthology/W17-5201 | |
| PWC | https://paperswithcode.com/paper/detecting-sarcasm-using-different-forms-of |
| Repo | |
| Framework | |
Automatic Difficulty Assessment for Chinese Texts
| Title | Automatic Difficulty Assessment for Chinese Texts |
| Authors | John Lee, Meichun Liu, Chun Yin Lam, Tak On Lau, Bing Li, Keying Li |
| Abstract | We present a web-based interface that automatically assesses reading difficulty of Chinese texts. The system performs word segmentation, part-of-speech tagging and dependency parsing on the input text, and then determines the difficulty levels of the vocabulary items and grammatical constructions in the text. Furthermore, the system highlights the words and phrases that must be simplified or re-written in order to conform to the user-specified target difficulty level. Evaluation results show that the system accurately identifies the vocabulary level of 89.9{%} of the words, and detects grammar points at 0.79 precision and 0.83 recall. |
| Tasks | Dependency Parsing, Language Acquisition, Part-Of-Speech Tagging |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3012/ |
| https://www.aclweb.org/anthology/I17-3012 | |
| PWC | https://paperswithcode.com/paper/automatic-difficulty-assessment-for-chinese |
| Repo | |
| Framework | |
Model evidence from nonequilibrium simulations
| Title | Model evidence from nonequilibrium simulations |
| Authors | Michael Habeck |
| Abstract | The marginal likelihood, or model evidence, is a key quantity in Bayesian parameter estimation and model comparison. For many probabilistic models, computation of the marginal likelihood is challenging, because it involves a sum or integral over an enormous parameter space. Markov chain Monte Carlo (MCMC) is a powerful approach to compute marginal likelihoods. Various MCMC algorithms and evidence estimators have been proposed in the literature. Here we discuss the use of nonequilibrium techniques for estimating the marginal likelihood. Nonequilibrium estimators build on recent developments in statistical physics and are known as annealed importance sampling (AIS) and reverse AIS in probabilistic machine learning. We introduce estimators for the model evidence that combine forward and backward simulations and show for various challenging models that the evidence estimators outperform forward and reverse AIS. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6772-model-evidence-from-nonequilibrium-simulations |
| http://papers.nips.cc/paper/6772-model-evidence-from-nonequilibrium-simulations.pdf | |
| PWC | https://paperswithcode.com/paper/model-evidence-from-nonequilibrium |
| Repo | |
| Framework | |
Crossing the border twice: Reimporting prepositions to alleviate L1-specific transfer errors
| Title | Crossing the border twice: Reimporting prepositions to alleviate L1-specific transfer errors |
| Authors | Johannes Gra{"e}n, Gerold Schneider |
| Abstract | |
| Tasks | Grammatical Error Correction, Language Acquisition, Word Alignment |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0303/ |
| https://www.aclweb.org/anthology/W17-0303 | |
| PWC | https://paperswithcode.com/paper/crossing-the-border-twice-reimporting |
| Repo | |
| Framework | |
IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations
| Title | IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations |
| Authors | Shangmin Guo, Kang Liu, Shizhu He, Cao Liu, Jun Zhao, Zhuoyu Wei |
| Abstract | The IJCNLP-2017 Multi-choice Question Answering(MCQA) task aims at exploring the performance of current Question Answering(QA) techniques via the realworld complex questions collected from Chinese Senior High School Entrance Examination papers and CK12 website1. The questions are all 4-way multi-choice questions writing in Chinese and English respectively that cover a wide range of subjects, e.g. Biology, History, Life Science and etc. And, all questions are restrained within the elementary and middle school level. During the whole procedure of this task, 7 teams submitted 323 runs in total. This paper describes the collected data, the format and size of these questions, formal run statistics and results, overview and performance statistics of different methods |
| Tasks | Question Answering |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4005/ |
| https://www.aclweb.org/anthology/I17-4005 | |
| PWC | https://paperswithcode.com/paper/ijcnlp-2017-task-5-multi-choice-question |
| Repo | |
| Framework | |
Sheffield at SemEval-2017 Task 9: Transition-based language generation from AMR.
| Title | Sheffield at SemEval-2017 Task 9: Transition-based language generation from AMR. |
| Authors | Gerasimos Lampouras, Andreas Vlachos |
| Abstract | This paper describes the submission by the University of Sheffield to the SemEval 2017 Abstract Meaning Representation Parsing and Generation task (SemEval 2017 Task 9, Subtask 2). We cast language generation from AMR as a sequence of actions (e.g., insert/remove/rename edges and nodes) that progressively transform the AMR graph into a dependency parse tree. This transition-based approach relies on the fact that an AMR graph can be considered structurally similar to a dependency tree, with a focus on content rather than function words. An added benefit to this approach is the greater amount of data we can take advantage of to train the parse-to-text linearizer. Our submitted run on the test data achieved a BLEU score of 3.32 and a Trueskill score of -22.04 on automatic and human evaluation respectively. |
| Tasks | Language Modelling, Machine Translation, Text Generation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2096/ |
| https://www.aclweb.org/anthology/S17-2096 | |
| PWC | https://paperswithcode.com/paper/sheffield-at-semeval-2017-task-9-transition |
| Repo | |
| Framework | |
Bingo at IJCNLP-2017 Task 4: Augmenting Data using Machine Translation for Cross-linguistic Customer Feedback Classification
| Title | Bingo at IJCNLP-2017 Task 4: Augmenting Data using Machine Translation for Cross-linguistic Customer Feedback Classification |
| Authors | Heba Elfardy, Manisha Srivastava, Wei Xiao, Jared Kramer, Tarun Agarwal |
| Abstract | The ability to automatically and accurately process customer feedback is a necessity in the private sector. Unfortunately, customer feedback can be one of the most difficult types of data to work with due to the sheer volume and variety of services, products, languages, and cultures that comprise the customer experience. In order to address this issue, our team built a suite of classifiers trained on a four-language, multi-label corpus released as part of the shared task on {``}Customer Feedback Analysis{''} at IJCNLP 2017. In addition to standard text preprocessing, we translated each dataset into each other language to increase the size of the training datasets. Additionally, we also used word embeddings in our feature engineering step. Ultimately, we trained classifiers using Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) Recurrent Neural Networks. Overall, we achieved a Macro-Average F-score between 48.7{%} and 56.0{%} for the four languages and ranked 3/12 for English, 3/7 for Spanish, 1/8 for French, and 2/7 for Japanese. | |
| Tasks | Feature Engineering, Machine Translation, Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4009/ |
| https://www.aclweb.org/anthology/I17-4009 | |
| PWC | https://paperswithcode.com/paper/bingo-at-ijcnlp-2017-task-4-augmenting-data |
| Repo | |
| Framework | |
Log-normality and Skewness of Estimated State/Action Values in Reinforcement Learning
| Title | Log-normality and Skewness of Estimated State/Action Values in Reinforcement Learning |
| Authors | Liangpeng Zhang, Ke Tang, Xin Yao |
| Abstract | Under/overestimation of state/action values are harmful for reinforcement learning agents. In this paper, we show that a state/action value estimated using the Bellman equation can be decomposed to a weighted sum of path-wise values that follow log-normal distributions. Since log-normal distributions are skewed, the distribution of estimated state/action values can also be skewed, leading to an imbalanced likelihood of under/overestimation. The degree of such imbalance can vary greatly among actions and policies within a single problem instance, making the agent prone to select actions/policies that have inferior expected return and higher likelihood of overestimation. We present a comprehensive analysis to such skewness, examine its factors and impacts through both theoretical and empirical results, and discuss the possible ways to reduce its undesirable effects. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6777-log-normality-and-skewness-of-estimated-stateaction-values-in-reinforcement-learning |
| http://papers.nips.cc/paper/6777-log-normality-and-skewness-of-estimated-stateaction-values-in-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/log-normality-and-skewness-of-estimated |
| Repo | |
| Framework | |
CIAL at IJCNLP-2017 Task 2: An Ensemble Valence-Arousal Analysis System for Chinese Words and Phrases
| Title | CIAL at IJCNLP-2017 Task 2: An Ensemble Valence-Arousal Analysis System for Chinese Words and Phrases |
| Authors | Zheng-Wen Lin, Yung-Chun Chang, Chen-Ann Wang, Yu-Lun Hsieh, Wen-Lian Hsu |
| Abstract | Sentiment lexicon is very helpful in dimensional sentiment applications. Because of countless Chinese words, developing a method to predict unseen Chinese words is required. The proposed method can handle both words and phrases by using an ADVWeight List for word prediction, which in turn improves our performance at phrase level. The evaluation results demonstrate that our system is effective in dimensional sentiment analysis for Chinese phrases. The Mean Absolute Error (MAE) and Pearson{'}s Correlation Coefficient (PCC) for Valence are 0.723 and 0.835, respectively, and those for Arousal are 0.914 and 0.756, respectively. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4015/ |
| https://www.aclweb.org/anthology/I17-4015 | |
| PWC | https://paperswithcode.com/paper/cial-at-ijcnlp-2017-task-2-an-ensemble |
| Repo | |
| Framework | |
CYUT at IJCNLP-2017 Task 3: System Report for Review Opinion Diversification
| Title | CYUT at IJCNLP-2017 Task 3: System Report for Review Opinion Diversification |
| Authors | Shih-Hung Wu, Su-Yu Chang, Liang-Pu Chen |
| Abstract | Review Opinion Diversification (RevOpiD) 2017 is a shared task which is held in International Joint Conference on Natural Language Processing (IJCNLP). The shared task aims at selecting top-k reviews, as a summary, from a set of re-views. There are three subtasks in RevOpiD: helpfulness ranking, rep-resentativeness ranking, and ex-haustive coverage ranking. This year, our team submitted runs by three models. We focus on ranking reviews based on the helpfulness of the reviews. In the first two models, we use linear regression with two different loss functions. First one is least squares, and second one is cross entropy. The third run is a random baseline. For both k=5 and k=10, our second model gets the best scores in the official evaluation metrics. |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4022/ |
| https://www.aclweb.org/anthology/I17-4022 | |
| PWC | https://paperswithcode.com/paper/cyut-at-ijcnlp-2017-task-3-system-report-for |
| Repo | |
| Framework | |
Learning Chordal Markov Networks via Branch and Bound
| Title | Learning Chordal Markov Networks via Branch and Bound |
| Authors | Kari Rantanen, Antti Hyttinen, Matti Järvisalo |
| Abstract | We present a new algorithmic approach for the task of finding a chordal Markov network structure that maximizes a given scoring function. The algorithm is based on branch and bound and integrates dynamic programming for both domain pruning and for obtaining strong bounds for search-space pruning. Empirically, we show that the approach dominates in terms of running times a recent integer programming approach (and thereby also a recent constraint optimization approach) for the problem. Furthermore, our algorithm scales at times further with respect to the number of variables than a state-of-the-art dynamic programming algorithm for the problem, with the potential of reaching 20 variables and at the same time circumventing the tight exponential lower bounds on memory consumption of the pure dynamic programming approach. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6781-learning-chordal-markov-networks-via-branch-and-bound |
| http://papers.nips.cc/paper/6781-learning-chordal-markov-networks-via-branch-and-bound.pdf | |
| PWC | https://paperswithcode.com/paper/learning-chordal-markov-networks-via-branch |
| Repo | |
| Framework | |
JUNLP at IJCNLP-2017 Task 3: A Rank Prediction Model for Review Opinion Diversification
| Title | JUNLP at IJCNLP-2017 Task 3: A Rank Prediction Model for Review Opinion Diversification |
| Authors | Monalisa Dey, Anupam Mondal, Dipankar Das |
| Abstract | IJCNLP-17 Review Opinion Diversification (RevOpiD-2017) task has been designed for ranking the top-k reviews of a product from a set of reviews, which assists in identifying a summarized output to express the opinion of the entire review set. The task is divided into three independent subtasks as subtask-A,subtask-B, and subtask-C. Each of these three subtasks selects the top-k reviews based on helpfulness, representativeness, and exhaustiveness of the opinions expressed in the review set individually. In order to develop the modules and predict the rank of reviews for all three subtasks, we have employed two well-known supervised classifiers namely, Na{"\i}ve Bayes and Logistic Regression on the top of several extracted features such as the number of nouns, number of verbs, and number of sentiment words etc from the provided datasets. Finally, the organizers have helped to validate the predicted outputs for all three subtasks by using their evaluation metrics. The metrics provide the scores of list size 5 as (0.80 (mth)) for subtask-A, (0.86 (cos), 0.87 (cos d), 0.71 (cpr), 4.98 (a-dcg), and 556.94 (wt)) for subtask B, and (10.94 (unwt) and 0.67 (recall)) for subtask C individually. |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4023/ |
| https://www.aclweb.org/anthology/I17-4023 | |
| PWC | https://paperswithcode.com/paper/junlp-at-ijcnlp-2017-task-3-a-rank-prediction |
| Repo | |
| Framework | |
Distributional Lesk: Effective Knowledge-Based Word Sense Disambiguation
| Title | Distributional Lesk: Effective Knowledge-Based Word Sense Disambiguation |
| Authors | Dieke Oele, Gertjan van Noord |
| Abstract | |
| Tasks | Learning Word Embeddings, Word Embeddings, Word Sense Disambiguation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6931/ |
| https://www.aclweb.org/anthology/W17-6931 | |
| PWC | https://paperswithcode.com/paper/distributional-lesk-effective-knowledge-based |
| Repo | |
| Framework | |
